Abstract: Examples include techniques to use intrinsic information when implementing a bit-flipping algorithm. An error correction control (ECC) decoder uses the intrinsic information to decode a low density parity count (LDPC) codeword. The intrinsic information including bits of a copy of a received LDPC codeword are compared to bits for variable nodes during an iteration of the bit-flipping algorithm to aid a determination as whether one or more bits for the variable nodes are to be flipped.

Abstract: One embodiment provides a memory controller. The memory controller includes a memory controller memory; a timestamp circuitry and a demarcation voltage (VDM) selection circuitry. The timestamp circuitry is to capture a current timer index from a timer circuitry in response to an initiation of a periodic patrol scrub and to compare the current timer index to a stored timestamp. The VDM selection circuitry is to update a state of a sub-block of a memory array, if the state is less than a threshold and a difference between the current timer index and the stored timestamp is nonzero. The timestamp circuitry is further to store the current timer index as a new timestamp.

Abstract: Technologies for correcting flipped bits prior to performing an error correction decode process include an apparatus that includes a memory to store a redundant set of codewords and a controller to read data from the memory. The controller selects a codeword from the redundant set of codewords to read from the memory, analyzes the selected codewords to determine whether the codeword contains uncorrectable errors, reads remaining codewords in the redundant set that correspond to the selected codeword, combines the remaining codewords together to generate a rebuilt codeword, flips bits in sections of the rebuilt codeword that differ from the selected codeword by a threshold amount, and performs an error correction decode process based on the rebuilt codeword.

Abstract: One embodiment provides a memory controller. The memory controller includes a memory controller memory; a timestamp circuitry and a demarcation voltage (VDM) selection circuitry. The timestamp circuitry is to capture a current timer index from a timer circuitry in response to an initiation of a periodic patrol scrub and to compare the current timer index to a stored timestamp. The VDM selection circuitry is to update a state of a sub-block of a memory array, if the state is less than a threshold and a difference between the current timer index and the stored timestamp is nonzero. The timestamp circuitry is further to store the current timer index as a new timestamp.

Abstract: One embodiment provides a silent data corruption (SDC) mitigation circuitry. The SDC mitigation circuitry includes a comparator circuitry and an SDC mitigation logic. The comparator circuitry is to compare a successful decoded codeword and a corresponding received codeword, the successful decoded codeword having been deemed a success by an error correction circuitry. The SDC mitigation logic is to reject the successful decoded codeword if a distance between the corresponding received codeword and the successful decoded codeword is greater than or equal to a threshold.

Abstract: These present disclosure provides devices and techniques to compress a list of integers. A circuit may include a sorter to sort a list of integers and a subtractor to determine a range of integers represented in the list and to recursively subdivide the range into sub-ranges. The circuit may also include a bit determiner to determine an amount of information (e.g., bits) to use to add indications of the integers in the list to a compresses list information element based on the range and the sub-ranges.

Abstract: Devices, systems, and methods that reduce the latency of detecting that a codeword is uncorrectable are disclosed and described. Such devices, systems, and methods allow the determination that a codeword is uncorrectable prior to determining error locations in the codeword, thus eliminating the need for such an error location search.

Abstract: One-sided soft reads can enable improved error-correction over regular reads without significantly increasing the latency for reads. In one example, a flash storage device includes an array of storage cells and a controller to access the array of storage cells. The controller is to perform at least one read of a storage cell to cause a read strobe to be applied at an expected read reference voltage and also cause one or more additional read strobes to be applied of the at voltages on only one side of the expected read reference voltage (e.g., which in some cases involves applying the additional one or more read strobes at a voltage with a slightly lower or higher magnitude than the magnitude of the expected read reference voltage). The controller can then provide a logic value and one or more bits indicating confidence or reliability of the logic value's accuracy based on an electrical response of the storage cell to the read strobe and the one or more additional read strobes.

Abstract: Provided are a method, system, and apparatus using reliability information from multiple storage units and a parity storage unit to recover data for a failed one of the storage units. A decoding operation of the codeword is performed in each of the storage units comprising the data storage units other than the target data storage unit and the parity storage unit to produce reliability information. In response to the decoding operation failing for at least one additional failed storage unit comprising the data and/or parity storage units other than the target data storage unit that failed to decode, reliability information is obtained for the data portion of the at least one additional failed storage unit. The reliability information obtained from the storage units other than the target data storage unit is used to produce corrected data for the data unit in the target data storage unit.

Abstract: Provided are an apparatus, non-volatile memory storage device and method for detecting drift in in non-volatile memory. A determination is made as to whether bits to write have more of a first value than a second value. Each of the bits are flipped to another of the first or second value when the bits have more of the first value than the second value. Indication is made whether the bits were flipped or not flipped. Parity is calculated for the bits and the bits and the parity for the bits are written to a location in the non-volatile memory. The bits at the location in the non-volatile memory are read and each of the bits having the first value are flipped to the second value and each of the bits having the second value are flipped to the first value in response to indication that the bits were flipped.

Abstract: A memory controller circuitry includes a timestamp circuitry and a demarcation voltage (VDM) selection circuitry. The timestamp circuitry is to capture a global timer index from a global timer having a granularity, G. The timestamp circuitry is further to fetch a timestamp for a memory block that includes a group of sub-blocks that includes a target sub-block. The demarcation voltage (VDM) selection circuitry is to fetch a combined count from a count store. The combined count represents a combined state. The combined state includes a target individual state of the target sub-block and a respective individual state of each of at least one other sub-block of the group of sub-blocks included in the memory block.

Abstract: A memory controller circuitry includes a timestamp circuitry and a demarcation voltage (VDM) selection circuitry. The timestamp circuitry is to capture a global timer index from a global timer having a granularity, G. The timestamp circuitry is further to fetch a timestamp for a memory block that includes a group of sub-blocks that includes a target sub-block. The demarcation voltage (VDM) selection circuitry is to fetch a combined count from a count store. The combined count represents a combined state. The combined state includes a target individual state of the target sub-block and a respective individual state of each of at least one other sub-block of the group of sub-blocks included in the memory block.

Abstract: In response to a write operation on a storage element in a non-volatile memory device, a count provided by a global counter is stored to indicate a time at which the write operation occurs on the storage element. In response to receiving a request perform a read operation on the storage element, a determination is made of a demarcation voltage to apply for performing the read operation on the storage element, based on a progress of the global counter since the write operation on the storage element.

Abstract: Provided are a method, system, and apparatus using reliability information from multiple storage units and a parity storage unit to recover data for a failed one of the storage units. A decoding operation of the codeword is performed in each of the storage units comprising the data storage units other than the target data storage unit and the parity storage unit to produce reliability information. In response to the decoding operation failing for at least one additional failed storage unit comprising the data and/or parity storage units other than the target data storage unit that failed to decode, reliability information is obtained for the data portion of the at least one additional failed storage unit. The reliability information obtained from the storage units other than the target data storage unit is used to produce corrected data for the data unit in the target data storage unit.

Abstract: Technologies for correcting flipped bits prior to performing an error correction decode process include an apparatus that includes a memory to store a redundant set of codewords and a controller to read data from the memory. The controller selects a codeword from the redundant set of codewords to read from the memory, analyzes the selected codewords to determine whether the codeword contains uncorrectable errors, reads remaining codewords in the redundant set that correspond to the selected codeword, combines the remaining codewords together to generate a rebuilt codeword, flips bits in sections of the rebuilt codeword that differ from the selected codeword by a threshold amount, and performs an error correction decode process based on the rebuilt codeword.

Abstract: Apparatus, systems, and methods for AES integrity check in memory are described. In one embodiment, a controller comprises logic to receive a write request from a host device to write a line of data to the memory device, determine a first plaintext cyclic redundancy check from the line of data, encrypt the line of data, encrypt the first plaintext CRC with a unique value to generate a first encrypted CRC, and store the encrypted line of data and the first encrypted CRC in memory. Other embodiments are also disclosed and claimed.

Abstract: Memory circuit defect correction in accordance with one aspect of the present description, logically divides a block of data bits into a plurality of data bit sections, each data bit section to be written into and stored in an associated memory section of a block of memory logically divided into a plurality memory sections. In one embodiment, for each data bit section and its associated memory section, the logical values of all the user data bits of the data bit section are selectively flipped so that the logical value of a user data bit to be written into a defective bitcell, matches the fixed read output of a defective bit cell. A bitcell in each memory section may be utilized to set a flip-flag to indicate whether or not the data bits of the memory section have been flipped. Other aspects are described herein.

Abstract: A predetermined pattern of bits is written to a non-volatile memory device prior to powering down the non-volatile memory device. A plurality of voltages are applied to the non-volatile memory device to determine which voltage of the plurality of voltages allows the predetermined pattern of bits to be read with a least amount of error. The determined voltage is set to be a demarcation voltage for reading from the non-volatile memory device.

Abstract: These present disclosure provides devices and techniques to compress a list of integers. A circuit may include a sorter to sort a list of integers and a subtractor to determine a range of integers represented in the list and to recursively subdivide the range into sub-ranges. The circuit may also include a bit determiner to determine an amount of information (e.g., bits) to use to add indications of the integers in the list to a compresses list information element based on the range and the sub-ranges.

Abstract: Embodiments are generally directed to errors and erasures decoding from multiple memory devices. An apparatus may include logic to store a portion of an error correction codeword in each of multiple memory devices, and logic to decode errors and erasures for the memory devices. The decoding of the errors and erasures includes reading the portions of the error correction codeword from a subset of the memory devices to generate a partial codeword, with the subset excluding at least one of the memory devices. The decoding of the errors and erasures further includes decoding errors and erasures of the plurality of memory devices based at least in part on the partial codeword if the errors and erasures can be decoded from the partial codeword, and, upon determining that the errors and erasures cannot be decoded from the partial codeword, then reading the one or more portions of the error correction codeword from the memory devices excluded from the first subset to generate a complete codeword.